xnnxax527 edited a comment on issue #15796: Model Quantization with CUDNN URL: https://github.com/apache/incubator-mxnet/issues/15796#issuecomment-520865110 Hi @xinyu-intel , I see you release the calibration and quantization code on Intel MKLDNN, thanks. I am so interested in quantizing gluoncv SSD model on GPU, but the mkldnn quantized ssd model can't run on ctx=mx.gpu(), what's the problem? the model should quantized with cudnn if i want to run on GPU? When run net(x), the error log is: `ipdb> net(x) *** mxnet.base.MXNetError: [00:17:29] src/imperative/./imperative_utils.h:558: Check failed: fcompute != nullptr: One of FStatefulCompute and FStatefulComputeEx must be registered for stateful operator _sg_mkldnn_conv Stack trace: [bt] (0) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x4f710b) [0x7f8a1582b10b] [bt] (1) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::imperative::PushOperator(mxnet::OpStatePtr const&, nnvm::Op const*, nnvm::NodeAttrs const&, mxnet::Context const&, std::vector<mxn et::engine::Var*, std::allocator<mxnet::engine::Var*> > const&, std::vector<mxnet::engine::Var*, std::allocator<mxnet::engine::Var*> > const&, std::vector<mxnet::Resource, std::allocator<mxnet::Resource> > const&, std::vector<mxnet: :NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector<unsigned int, std::allocator<unsigned int> > const&, std::vector<mxnet::OpReqType, std::allocato r<mxnet::OpReqType> > const&, mxnet::DispatchMode)+0x9cf) [0x7f8a17e3447f] [bt] (2) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::Imperative::InvokeOp(mxnet::Context const&, nnvm::NodeAttrs const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType> > const&, mxnet::DispatchMode, mxnet::OpStatePtr)+0xa71) [0x7f8a17e368d1] [bt] (3) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x2b0c990) [0x7f8a17e40990] [bt] (4) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x2b0e5c4) [0x7f8a17e425c4] [bt] (5) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::imperative::RunGraph(bool, nnvm::IndexedGraph const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, unsig ned long, unsigned long, std::vector<mxnet::OpReqType, std::allocator<mxnet::OpReqType> >&&, std::vector<unsigned int, std::allocator<unsigned int> >&&, std::vector<mxnet::OpStatePtr, std::allocator<mxnet::OpStatePtr> >*, std::vecto r<mxnet::DispatchMode, std::allocator<mxnet::DispatchMode> > const&, bool, std::vector<mxnet::TShape, std::allocator<mxnet::TShape> >*)+0x208) [0x7f8a17e42a58] [bt] (6) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::CachedOp::DynamicForward(mxnet::Context const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector <mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, bool)+0x124e) [0x7f8a17e10e6e] [bt] (7) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(mxnet::CachedOp::Forward(std::shared_ptr<mxnet::CachedOp> const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&, std::vector<mxnet::NDArray*, std::allocator<mxnet::NDArray*> > const&)+0xb55) [0x7f8a17e16825] [bt] (8) /home/jiashen.hjs/anaconda2/envs/py35/lib/python3.5/site-packages/mxnet/libmxnet.so(MXInvokeCachedOp+0x4ab) [0x7f8a17d2ac9b]`
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services